Context Engineering

The practice, in LLM-based systems, of deliberately selecting, structuring, and injecting the information an AI model sees on each call — beyond just the user's latest message — so that outputs are grounded, relevant, and aligned with the user's actual situation. Typical context sources include screen state, recent user actions, chat history, retrieved documentation (RAG), and encoded response preferences. Context engineering is particularly important for accessibility assistants, where a screen reader user's ambiguous query ('how do I do this?') can only be answered correctly if the system knows what application is active, what element is focused, and what the user has already tried.